The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 168
Enzo Souza
enzosouza01
AI & ML interests
Working on AI projects: transformers, datasets and fine-tuning.
Recent Activity
updated a dataset 5 days ago
enzosouza01/cs229-security-2024 published a dataset 5 days ago
enzosouza01/cs229-security-2024 liked a model 5 days ago
YuyaoTechnology/MatterSeek-New-Materials-Reverse-DesignOrganizations
None yet
upvoted 2
papers about 1 month ago